TY - JOUR
T1 - A multi-fidelity wind surface pressure assessment via machine learning
T2 - A high-rise building case
AU - Glumac, Anina Šarkić
AU - Jadhav, Onkar
AU - Despotović, Vladimir
AU - Blocken, Bert
AU - Bordas, Stephane P.A.
N1 - Funding Information:
The authors A.S.G. O.J. and S.P.A.B. would like to acknowledge the support of the ”Fonds National de la Recherche, Luxembourg” (FNR) for funding the CORE Junior project DATA4WIND - ”Data-Driven Approach for Urban Wind Energy Harvesting”, C19/SR/13639741. The co-author S.P.A.B. received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 811099 TWINNING Project DRIVEN for the University of Luxembourg. Numerical simulations were run on the HPC centre of University of Luxembourg.
Funding Information:
The authors A.S.G., O.J. and S.P.A.B. would like to acknowledge the support of the ”Fonds National de la Recherche, Luxembourg” (FNR) for funding the CORE Junior project DATA4WIND - ”Data-Driven Approach for Urban Wind Energy Harvesting” , C19/SR/13639741 . The co-author S.P.A.B. received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 811099 TWINNING Project DRIVEN for the University of Luxembourg. Numerical simulations were run on the HPC centre of University of Luxembourg.
Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/4/15
Y1 - 2023/4/15
N2 - Computational fluid dynamics (CFD) represents an attractive tool for estimating wind pressures and wind loads on high-rise buildings. The CFD analyses can be conducted either by low-fidelity simulations (RANS) or by high-fidelity ones (LES). The low-fidelity model can efficiently estimate wind pressures over a large range of wind directions, but it generally lacks accuracy. On the other hand, the high-fidelity model generally exhibits satisfactory accuracy, yet, the high computational cost can limit the number of approaching wind angles that can be considered. In order to take advantage of the main benefits of these two CFD approaches, a multi-fidelity machine learning framework is investigated that aims to ensure the simulation accuracy while maintaining the computational efficiency. The study shows that the accurate prediction of distributions of mean and rms pressure over a high-rise building for the entire wind rose can be obtained by utilizing only 3 LES-related wind directions. The artificial neural network is shown to perform best among considered machine learning models. Moreover, hyperparameter optimization significantly improves the model predictions, increasing the R2 value in the case of rms pressure by 60%. Dominant and ineffective features are determined that provide a route to solve a similar application more effectively.
AB - Computational fluid dynamics (CFD) represents an attractive tool for estimating wind pressures and wind loads on high-rise buildings. The CFD analyses can be conducted either by low-fidelity simulations (RANS) or by high-fidelity ones (LES). The low-fidelity model can efficiently estimate wind pressures over a large range of wind directions, but it generally lacks accuracy. On the other hand, the high-fidelity model generally exhibits satisfactory accuracy, yet, the high computational cost can limit the number of approaching wind angles that can be considered. In order to take advantage of the main benefits of these two CFD approaches, a multi-fidelity machine learning framework is investigated that aims to ensure the simulation accuracy while maintaining the computational efficiency. The study shows that the accurate prediction of distributions of mean and rms pressure over a high-rise building for the entire wind rose can be obtained by utilizing only 3 LES-related wind directions. The artificial neural network is shown to perform best among considered machine learning models. Moreover, hyperparameter optimization significantly improves the model predictions, increasing the R2 value in the case of rms pressure by 60%. Dominant and ineffective features are determined that provide a route to solve a similar application more effectively.
KW - LES
KW - Machine learning
KW - RANS
KW - Wind loading
UR - http://www.scopus.com/inward/record.url?scp=85149634014&partnerID=8YFLogxK
U2 - 10.1016/j.buildenv.2023.110135
DO - 10.1016/j.buildenv.2023.110135
M3 - Article
AN - SCOPUS:85149634014
SN - 0360-1323
VL - 234
JO - Building and Environment
JF - Building and Environment
M1 - 110135
ER -